linux/arch/csky/abiv2/memset.S
Guo Ren c5af58b769 csky: Library functions
This patch adds string optimize codes and some auxiliary codes.

Signed-off-by: Chen Linfei <linfei_chen@c-sky.com>
Signed-off-by: Mao Han <han_mao@c-sky.com>
Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
2018-10-26 00:54:24 +08:00

84 lines
1.7 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#include <linux/linkage.h>
#include "sysdep.h"
.weak memset
ENTRY(__memset)
ENTRY(memset)
/* Test if len less than 4 bytes. */
mov r12, r0
cmplti r2, 8
bt .L_set_by_byte
andi r13, r0, 3
movi r19, 4
/* Test if dest is not 4 bytes aligned. */
bnez r13, .L_dest_not_aligned
/* Hardware can handle unaligned access directly. */
.L_dest_aligned:
zextb r3, r1
lsli r1, 8
or r1, r3
lsli r3, r1, 16
or r3, r1
/* If dest is aligned, then copy. */
zext r18, r2, 31, 4
/* Test if len less than 16 bytes. */
bez r18, .L_len_less_16bytes
LABLE_ALIGN
.L_len_larger_16bytes:
stw r3, (r0, 0)
stw r3, (r0, 4)
stw r3, (r0, 8)
stw r3, (r0, 12)
PRE_BNEZAD (r18)
addi r0, 16
BNEZAD (r18, .L_len_larger_16bytes)
.L_len_less_16bytes:
zext r18, r2, 3, 2
andi r2, 3
bez r18, .L_set_by_byte
.L_len_less_16bytes_loop:
stw r3, (r0, 0)
PRE_BNEZAD (r18)
addi r0, 4
BNEZAD (r18, .L_len_less_16bytes_loop)
/* Test if len less than 4 bytes. */
.L_set_by_byte:
zext r18, r2, 2, 0
bez r18, .L_return
.L_set_by_byte_loop:
stb r1, (r0, 0)
PRE_BNEZAD (r18)
addi r0, 1
BNEZAD (r18, .L_set_by_byte_loop)
.L_return:
mov r0, r12
rts
/* If dest is not aligned, just set some bytes makes the dest
align. */
.L_dest_not_aligned:
sub r13, r19, r13
sub r2, r13
.L_dest_not_aligned_loop:
/* Makes the dest align. */
stb r1, (r0, 0)
PRE_BNEZAD (r13)
addi r0, 1
BNEZAD (r13, .L_dest_not_aligned_loop)
cmplti r2, 8
bt .L_set_by_byte
/* Check whether the src is aligned. */
jbr .L_dest_aligned
ENDPROC(memset)
ENDPROC(__memset)